Glottal Closure Instant Detection Research Articles

Glottal Inverse Filtering Using Probabilistic Weighted Linear Prediction

Glottal inverse filtering is a noninvasive method for getting the glottal flow estimate from the speech. In this paper, we propose a method for glottal inverse filtering based on probabilistic weighted linear prediction PWLP in which the speech is assumed to be the output of an all-pole filter with glottal flow as an excitation. First, we introduce a probabilistic interpretation of the WLP, and we propose a probabilistic temporal weighting as convolution of a binary vector and a fixed window. We construct the posterior distribution based on the PWLP likelihood and a Gaussian prior on the filter coefficients. The parameters are estimated using the Gibbs sampling. The experiments are performed using the Lijencrants–Fant LF model based synthetic data, a physical model based synthetic data of different vowels and real speech data. Results demonstrate that the proposed method outperforms the best of the existing state-of-the-art methods in terms of the normalized amplitude quotient by 0.035 and 0.12 for the LF model and physical model based synthetic data, respectively. The results based on real speech data show that the glottal flow estimated by the proposed method in the closed phase is flatter and has less formant ripple compared to existing state-of-the-art methods. We also show two key features of the proposed method: first, the proposed method does not need prior detection of glottal closure or opening instants. The temporal weights are learnt in a data-driven manner, which is often found to be high near the closed phase of the glottal cycle, second, the Gaussian prior helps in estimating the filter coefficients when the closed phase duration is small.

PSFM—A Probabilistic Source Filter Model for Noise Robust Glottal Closure Instant Detection

Accurate estimation of glottal closure instant (GCI) enables several pitch synchronous speech analysis, such as prosody modifications, glottal inverse filtering, and study of pathological speech. We propose a probabilistic source-filter model (PSFM) for voiced speech, where the source is modeled using the Bernoulli Gaussian distribution, which models the GCI locations and the all-pole filter coefficients are modeled using Gaussian distribution. The probability of GCIs at each speech sample is estimated using the Gibbs sampling. We propose a cost to estimate the exact GCI locations using the N-best dynamic programming. A key feature of the proposed PSFM is that it allows us to include the second-order statistics of the noise for estimating the GCI locations, thereby resulting in a noise robust GCI detection technique, although it has high computational complexity. Evaluation on archivable priority list actual-word database (APLAWD) database shows the proposed algorithm performs at par with the state-of-the-art GCI detection method on clean speech. However, when evaluated in noisy conditions using five types of noises at six different signal-to-noise ratio (SNR) levels, we observe that the proposed method performs better than the best of the existing GCI detection scheme, particularly at low SNR condition indicating the noise robustness of the proposed method.

Accurate Estimation of Glottal Closure Instants and Glottal Opening Instants from Electroglottographic Signal Using Variational Mode Decomposition

The objective of the proposed work is to accurately estimate the glottal closure instants (GCIs) and glottal opening instant (GOIs) from electroglottographic (EGG) signals. This work also addresses the issues with existing EGG-based GCI/GOI detection methods. GCIs are the instants at which excitation to the vocal tract is maximum and GOIs, on the other hand, have minimum excitation compared to GCIs. Both these instants occur instantaneously with a fundamental frequency defined for each glottal cycle in a given EGG signal. Accurate detection of these instants from the EGG signal is essential for the performance evaluation of GCIs and GOIs estimated from the speech signal directly. This work proposes a new method for accurate detection of GCIs and GOIs from the EGG signal using variational mode decomposition (VMD) algorithm. The EGG signal has been decomposed into sub-signals using the VMD algorithm. It is shown that VMD captures the center frequency close to the fundamental frequency of the EGG signal through one of its modes. This property of the corresponding mode helps to estimate GCIs and GOIs from the same. Besides, instantaneous pitch frequency is estimated from the obtained GCIs. The proposed method has been evaluated on the CMU-arctic database for GCI/GOI estimation and the Keele pitch extraction reference database for instantaneous pitch frequency estimation. The effectiveness of the proposed method is confirmed by comparison with state-of-the-art methods. Experimental results show that the proposed method has better accuracy and identification rate compared to state-of-the-art methods.

Robust glottal closure instant detection by jointly exploiting stationary wavelet transform and harmonic superposition

This study jointly utilizes stationary wavelet transform (SWT) and harmonic superposition (HS) techniques to locate zero-crossings closely related to glottal closure instants (GCI). The entire process is performed directly on voiced speech signals without referring to the linear prediction residual or voiced source signal derived by inverse filtering. Subsequent to the multi-scale SWT decomposition, a linear phase FIR filter is introduced to translate positive zero-crossings into pulse-like features. While the product across the approximation coefficients in various SWT levels sharpens impulse features, the HS is employed to sieve out the main pulses corresponding GCIs. The advantages of using the proposed SWT---HS scheme for GCI detection are examined using the PTDB-TUG database. Compared with the other two advanced methods, namely the SEDREAMS and ZFR, without the assistance of any refining process the proposed SWT---HS not only renders better accuracy in GCI positioning but exhibits superior robustness against additive noise.

Detection of Glottal Closure Instants Based on the Microcanonical Multiscale Formalism

This paper presents a novel algorithm for automatic detection of Glottal Closure Instants (GCI) from the speech signal. Our approach is based on a novel multiscale method that relies on precise estimation of a multiscale parameter at each time instant in the signal domain. This parameter quantifies the degree of signal singularity at each sample from a multi-scale point of view and thus its value can be used to classify signal samples accordingly. We use this property to develop a simple algorithm for detection of GCIs and we show that for the case of clean speech, our algorithm performs almost as well as a recent state-of-the-art method. Next, by performing a comprehensive comparison in presence of 14 different types of noises, we show that our method is more accurate (particularly for very low SNRs). Our method has lower computational times compared to others and does not rely on an estimate of pitch period or any critical choice of parameters.

Evaluation of glottal closure instant detection in a range of voice qualities

Recently developed speech technology platforms, such as statistical speech synthesis and voice transformation systems, facilitate the modification of voice characteristics. To fully exploit the potential of such platforms, speech analysis algorithms need to be able to handle the different acoustic characteristics of a variety of voice qualities. Glottal closure instant (GCI) detection is typically required in the analysis stages, and thus the importance of robust GCI algorithms is evident. The current study examines some important analysis signals relevant to GCI detection, for a range of phonation types. Furthermore, a new algorithm is proposed which builds on an existing GCI algorithm to optimise the performance when analysing speech involving different phonation types. Results suggest improvements in the GCI detection rate for creaky voice due to a reduction in false positives. When there is a lack of prominent peaks in the Linear Prediction residual, as found for breathy and harsh voice, the results further indicate some enhancement of GCI identification accuracy for the proposed method.

Detection of Glottal Closure Instants From Speech Signals: A Quantitative Review

The pseudo-periodicity of voiced speech can be exploited in several speech processing applications. This requires however that the precise locations of the glottal closure instants (GCIs) are available. The focus of this paper is the evaluation of automatic methods for the detection of GCIs directly from the speech waveform. Five state-of-the-art GCI detection algorithms are compared using six different databases with contemporaneous electroglottographic recordings as ground truth, and containing many hours of speech by multiple speakers. The five techniques compared are the Hilbert Envelope-based detection (HE), the Zero Frequency Resonator-based method (ZFR), the Dynamic Programming Phase Slope Algorithm (DYPSA), the Speech Event Detection using the Residual Excitation And a Mean-based Signal (SEDREAMS) and the Yet Another GCI Algorithm (YAGA). The efficacy of these methods is first evaluated on clean speech, both in terms of reliabililty and accuracy. Their robustness to additive noise and to reverberation is also assessed. A further contribution of the paper is the evaluation of their performance on a concrete application of speech processing: the causal-anticausal decomposition of speech. It is shown that for clean speech, SEDREAMS and YAGA are the best performing techniques, both in terms of identification rate and accuracy. ZFR and SEDREAMS also show a superior robustness to additive noise and reverberation.

Glottal closure instant and voice source analysis using time-scale lines of maximum amplitude

1Time-scale representation of voiced speech is applied to voice quality analysis, by introducing the Line of Maximum Amplitude (LoMA) method. This representation takes advantage of the tree patterns observed for voiced speech periods in the time-scale domain. For each period, the optimal LoMA is computed by linking amplitude maxima at each scale of a wavelet transform, using a dynamic programming algorithm. A time-scale analysis of the linear acoustic model of speech production shows several interesting properties. The LoMA points to the glottal closure instants. The LoMA phase delay is linked to the voice open quotient. The cumulated amplitude along the LoMA is related to voicing amplitude. The LoMA spectral centre of gravity is an indication of voice spectral tilt. Following these theoretical considerations, experimental results are reported. Comparative evaluation demonstrates that the LoMA is an effective method for the detection of Glottal Closure Instants (GCI). The effectiveness of LoMA analysis for open quotient, amplitude and spectral tilt estimations is also discussed with the help of some examples.

On the detection of pitch marks using a robust multi-phase algorithm

A large number of methods for identifying glottal closure instants (GCIs) in voiced speech have been proposed in recent years. In this paper, we propose to take advantage of both glottal and speech signals in order to increase the accuracy of detection of GCIs. All aspects of this particular issue, from determining speech polarity to handling a delay between glottal and corresponding speech signal, are addressed. A robust multi-phase algorithm (MPA), which combines different methods applied on both signals in a unique way, is presented. Within the process, a special attention is paid to determination of speech waveform polarity, as it was found to be considerably influencing the performance of the detection algorithms. Another feature of the proposed method is that every detected GCI is given a confidence score, which allows to locate potentially inaccurate GCI subsequences. The performance of the proposed algorithm was tested and compared with other freely available GCI detection algorithms. The MPA algorithm was found to be more robust in terms of detection accuracy over various sets of sentences, languages and phone classes. Finally, some pitfalls of the GCI detection are discussed.

Comparison between DyWT- and EGG-based estimation of glottal closure instant for speech signal

Recently, wavelet transform has found many applications. Mallat has shown that, with a proper choice of wavelet function, the local maxima of wavelet transformed signal indicate the position of the signal sharp variation points. Since the glottal closure causes sharp changes in the derivative of air flow in the glottis and transient in the speech signal, wavelet analysis can be used for detection of glottal closure instant (GCI) from the speech signal. It is known that the point of maximum negative value in a differentiated EGG signal agrees well with the closing time of the vocal folds. Due to the limited practical utility of the EGG signal, however, a speech-only-based GCI detection method is still needed. In this paper, GCI detection algorithm based on the dyadic wavelet transform (DyWT) is proposed and experimental results are shown. Using the EGG signal as a reference, experimental results are analyzed and discussed for evaluation of its performance. Preliminary experimental results show that DyWT-based GCI detection method has some speaker dependency and wavelet transformed speech signal at scale 4 gives more reliable GCI information than that of others. [This work has been partially supported by a grant from Korea Science and Engineering Foundation (KOSEF 971-0917- 103-2).]

A Frobenius norm approach to glottal closure detection from the speech signal

The detection of glottal closure instants has been a necessary step in several applications of speech processing, such as voice source analysis, speech prosody manipulation and speech synthesis. The paper presents a new algorithm for glottal closure detection that compares favorably with other methods available in terms of robustness and computational efficiency. The authors propose to use the singular value decomposition (SVD) approach to detect the instants of glottal closure from the speech signal. The proposed SVD method amounts to calculating the Frobenius norms of signal matrices and therefore is computationally efficient. Moreover, it produces well-defined and reliable peaks that indicate the instants of glottal closure. Finally, with the introduction of the total linear least squares technique, two other proposed methods are reinvestigated and unified into the SVD framework. >